{"id":"https://openalex.org/W2136348312","doi":"https://doi.org/10.1002/meet.2014.14505101150","title":"Towards building a collection of web archiving research articles","display_name":"Towards building a collection of web archiving research articles","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2136348312","doi":"https://doi.org/10.1002/meet.2014.14505101150","mag":"2136348312"},"language":"en","primary_location":{"id":"doi:10.1002/meet.2014.14505101150","is_oa":true,"landing_page_url":"https://doi.org/10.1002/meet.2014.14505101150","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.2014.14505101150","source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"0044-7870","issn":["0044-7870","1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.2014.14505101150","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005823477","display_name":"Brenda Reyes Ayala","orcid":"https://orcid.org/0000-0002-9342-3832"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brenda Reyes Ayala","raw_affiliation_strings":["Library and Information Science University of North Texas  Denton TX 76203","Library and Information Science; University of North Texas; Denton TX 76203"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Library and Information Science University of North Texas  Denton TX 76203","institution_ids":["https://openalex.org/I123534392"]},{"raw_affiliation_string":"Library and Information Science; University of North Texas; Denton TX 76203","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089085275","display_name":"Cornelia Caragea","orcid":"https://orcid.org/0000-0002-5664-2163"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cornelia Caragea","raw_affiliation_strings":["Computer Science and Engineering University of North Texas  Denton TX 76203","Computer Science and Engineering University of North Texas Denton TX 76203"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering University of North Texas  Denton TX 76203","institution_ids":["https://openalex.org/I123534392"]},{"raw_affiliation_string":"Computer Science and Engineering University of North Texas Denton TX 76203","institution_ids":["https://openalex.org/I123534392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5005823477","https://openalex.org/A5089085275"],"corresponding_institution_ids":["https://openalex.org/I123534392"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.20667649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"51","issue":"1","first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8799397945404053},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.756159782409668},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7310482263565063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7151781320571899},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6343380212783813},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5842663049697876},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.5669424533843994},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4781516492366791},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4434921443462372},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3317192494869232},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06408742070198059}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8799397945404053},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.756159782409668},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7310482263565063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7151781320571899},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6343380212783813},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5842663049697876},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.5669424533843994},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4781516492366791},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4434921443462372},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3317192494869232},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06408742070198059},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1002/meet.2014.14505101150","is_oa":true,"landing_page_url":"https://doi.org/10.1002/meet.2014.14505101150","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.2014.14505101150","source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"0044-7870","issn":["0044-7870","1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"},{"id":"pmh:info:ark/67531/metadc287986","is_oa":false,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc287986/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Internet Preservation Consortium (IIPC) General Assembly, May 19-23, 2014. Paris, France","raw_type":"Presentation"},{"id":"pmh:info:ark/67531/metadc461721","is_oa":false,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc461721/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Association for Information Science and Technology (ASIS&T) Annual Meeting, October 31-November 5, 2014. Seattle, WA, United States","raw_type":"Paper"}],"best_oa_location":{"id":"doi:10.1002/meet.2014.14505101150","is_oa":true,"landing_page_url":"https://doi.org/10.1002/meet.2014.14505101150","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.2014.14505101150","source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"0044-7870","issn":["0044-7870","1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2136348312.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W82093824","https://openalex.org/W173995639","https://openalex.org/W1481372933","https://openalex.org/W1489992655","https://openalex.org/W1525770891","https://openalex.org/W1536940955","https://openalex.org/W1550206324","https://openalex.org/W1663973292","https://openalex.org/W1869416969","https://openalex.org/W1987391925","https://openalex.org/W2029341294","https://openalex.org/W2043976122","https://openalex.org/W2072897447","https://openalex.org/W2081933028","https://openalex.org/W2083089853","https://openalex.org/W2107756543","https://openalex.org/W2151809999","https://openalex.org/W2241724323","https://openalex.org/W2253675773","https://openalex.org/W3216833688","https://openalex.org/W4212863985","https://openalex.org/W4238591974","https://openalex.org/W4247980638"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W2137810919","https://openalex.org/W4255854114","https://openalex.org/W4385695127"],"abstract_inverted_index":{"ABSTRACT":[0],"The":[1,95],"field":[2,21],"of":[3,15,34,43,62,73,122,151],"Web":[4,44,78,90,134,141,152],"Archiving":[5,45,79,153],"exists":[6],"in":[7,148],"a":[8,31,47,60,70,77],"fluid,":[9],"fragmented,":[10],"and":[11,25,36,81,91,114,116],"heterogeneous":[12],"state.":[13],"Part":[14],"the":[16,41,65,89,111,120,133,149],"problem":[17],"is":[18,22,28],"that":[19,108,138],"this":[20],"relatively":[23],"new":[24],"its":[26],"literature":[27],"scattered":[29],"across":[30],"wide":[32],"range":[33],"journal":[35],"conference":[37],"venues.":[38],"This":[39,53],"makes":[40],"state":[42],"as":[46,136,154],"discipline":[48],"particularly":[49],"difficult":[50],"to":[51,58,84,128],"ascertain.":[52],"paper":[54],"presents":[55],"an":[56,155],"approach":[57],"building":[59],"collection":[61],"articles":[63,74],"about":[64,140],"subject.":[66],"We":[67,106,143],"begin":[68],"with":[69],"small":[71],"dataset":[72],"taken":[75],"from":[76,132],"Bibliography":[80],"then":[82,99],"proceed":[83],"expand":[85],"it":[86],"by":[87,109],"crawling":[88],"collecting":[92],"additional":[93],"documents.":[94],"crawled":[96],"documents":[97,131,137],"are":[98,126,139],"classified":[100],"using":[101,119],"machine":[102],"learning":[103],"classification":[104],"techniques.":[105],"show":[107],"extracting":[110],"documents\u2019":[112],"titles":[113],"abstracts":[115],"representing":[117],"them":[118],"\u201cbag":[121],"words\u201d":[123],"approach,":[124],"we":[125],"able":[127],"accurately":[129],"identify":[130],"crawler":[135],"Archiving.":[142],"also":[144],"discuss":[145],"our":[146],"results":[147],"context":[150],"emerging":[156],"field.":[157]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2025-10-10T00:00:00"}